FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding
Automated segmentation and evaluation of carotid plaques ultrasound images is of great significance for the diagnosis and early intervention of high-risk groups of cardiovascular and cerebrovascular diseases. However, it remains challenging to develop such solutions due to the relatively low quality...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/3/887 |
| _version_ | 1797484782357053440 |
|---|---|
| author | Yanhan Li Lian Zou Li Xiong Fen Yu Hao Jiang Cien Fan Mofan Cheng Qi Li |
| author_facet | Yanhan Li Lian Zou Li Xiong Fen Yu Hao Jiang Cien Fan Mofan Cheng Qi Li |
| author_sort | Yanhan Li |
| collection | DOAJ |
| description | Automated segmentation and evaluation of carotid plaques ultrasound images is of great significance for the diagnosis and early intervention of high-risk groups of cardiovascular and cerebrovascular diseases. However, it remains challenging to develop such solutions due to the relatively low quality of ultrasound images and heterogenous characteristics of carotid plaques. To address those problems, in this paper, we propose a novel deep convolutional neural network, FRDD-Net, with an encoder–decoder architecture to automatically segment carotid plaques. We propose the feature remapping modules (FRMs) and incorporate them into the encoding and decoding blocks to ameliorate the reliability of acquired features. We also propose a new dense decoding mechanism as part of the decoder, thus promoting the utilization efficiency of encoded features. Additionally, we construct a compound loss function to train our network to further enhance its robustness in the face of numerous cases. We train and test our network in multiple carotid plaque ultrasound datasets and our method yields the best performance compared to other state-of-the-art methods. Further ablation studies consistently show the advancement of our proposed architecture. |
| first_indexed | 2024-03-09T23:09:24Z |
| format | Article |
| id | doaj.art-009935f344f8467e84cd16be8583760a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T23:09:24Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-009935f344f8467e84cd16be8583760a2023-11-23T17:47:00ZengMDPI AGSensors1424-82202022-01-0122388710.3390/s22030887FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense DecodingYanhan Li0Lian Zou1Li Xiong2Fen Yu3Hao Jiang4Cien Fan5Mofan Cheng6Qi Li7Electronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaCardiovascular Ultrasound Department, Zhongnan Hospital of Wuhan University, Wuhan 430071, ChinaDepartment of Ultrasound, Central Hospital of Wuhan, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430014, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaAutomated segmentation and evaluation of carotid plaques ultrasound images is of great significance for the diagnosis and early intervention of high-risk groups of cardiovascular and cerebrovascular diseases. However, it remains challenging to develop such solutions due to the relatively low quality of ultrasound images and heterogenous characteristics of carotid plaques. To address those problems, in this paper, we propose a novel deep convolutional neural network, FRDD-Net, with an encoder–decoder architecture to automatically segment carotid plaques. We propose the feature remapping modules (FRMs) and incorporate them into the encoding and decoding blocks to ameliorate the reliability of acquired features. We also propose a new dense decoding mechanism as part of the decoder, thus promoting the utilization efficiency of encoded features. Additionally, we construct a compound loss function to train our network to further enhance its robustness in the face of numerous cases. We train and test our network in multiple carotid plaque ultrasound datasets and our method yields the best performance compared to other state-of-the-art methods. Further ablation studies consistently show the advancement of our proposed architecture.https://www.mdpi.com/1424-8220/22/3/887ultrasoundsegmentationdeep convolutional neural networkscarotid plaquesencoder–decoder |
| spellingShingle | Yanhan Li Lian Zou Li Xiong Fen Yu Hao Jiang Cien Fan Mofan Cheng Qi Li FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding Sensors ultrasound segmentation deep convolutional neural networks carotid plaques encoder–decoder |
| title | FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding |
| title_full | FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding |
| title_fullStr | FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding |
| title_full_unstemmed | FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding |
| title_short | FRDD-Net: Automated Carotid Plaque Ultrasound Images Segmentation Using Feature Remapping and Dense Decoding |
| title_sort | frdd net automated carotid plaque ultrasound images segmentation using feature remapping and dense decoding |
| topic | ultrasound segmentation deep convolutional neural networks carotid plaques encoder–decoder |
| url | https://www.mdpi.com/1424-8220/22/3/887 |
| work_keys_str_mv | AT yanhanli frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT lianzou frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT lixiong frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT fenyu frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT haojiang frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT cienfan frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT mofancheng frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding AT qili frddnetautomatedcarotidplaqueultrasoundimagessegmentationusingfeatureremappinganddensedecoding |